A Simple yet Effective Method for Sentence Ordering

Aili Shen, Timothy Baldwin


Abstract
Sentence ordering is the task of arranging a given bag of sentences so as to maximise the coherence of the overall text. In this work, we propose a simple yet effective training method that improves the capacity of models to capture overall text coherence based on training over pairs of sentences/segments. Experimental results show the superiority of our proposed method in in- and cross-domain settings. The utility of our method is also verified over a multi-document summarisation task.
Anthology ID:
2021.sigdial-1.16
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
154–160
Language:
URL:
https://aclanthology.org/2021.sigdial-1.16
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.16.pdf
Video:
 https://www.youtube.com/watch?v=HcurPPqHcrY